Real time query trends with multi-document summarization

At least one computer-readable storage medium encoded with executable instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

• receiving an indication of a search topic that is popular, the search topic that is popular being related to a particular entity;
• in response to receiving the indication of the search topic that is popular, identifying a content feed from an electronic source of published information that includes content published less than a threshold period of time prior to the search topic becoming popular, the content of the content feed including metadata;
• determining whether the content, of the identified content feed, published less than the threshold period of time prior to the search topic becoming popular is relevant to the search topic;
• in response to a determination that the content, of the identified content feed, published less than the threshold period of time prior to the search topic becoming popular is relevant to the search topic:
• analyzing the content, of the identified content feed, published less than the threshold period of time prior to the search topic becoming popular, analyzing the content comprising determining that the content and metadata of the content feed are related to the same particular entity as the search topic;
• determining a reason that the search topic is popular based on the analysis, determining the reason comprising, when the content identifies the search topic, providing at least some of the content as the reason that the search topic is popular;
• and
• presenting to a user the search topic that is popular and the determined reason that the search topic is popular;
• and
• summarizing content of more than one content feed when the content of more than one content feed relates to the same particular entity as the search topic.

A system comprising:

• at least one computer;
• and
• at least one computer-readable storage medium coupled to the at least one computer having instructions stored thereon which, when executed by the at least one computer, causes the at least one computer to perform operations comprising:
• receiving an indication of a search topic that is popular, the search topic that is popular being related to a particular entity;
• in response to receiving the indication of the search topic that is popular, identifying a content feed from an electronic source of published information that includes content published less than a threshold period of time prior to the search topic becoming popular, the content of the content feed including metadata;
• determining whether the content, of the identified content feed, published less than the threshold period of time prior to the search topic becoming popular is relevant to the search topic;
• in response to a determination that the content, of the identified content feed, published less than the threshold period of time prior to the search topic becoming popular is relevant to the search topic:
• analyzing the content, of the identified content feed, published less than the threshold period of time prior to the search topic becoming popular, analyzing the content comprising determining that the content and metadata of the content feed are related to the same particular entity as the search topic;
• determining a reason that the search topic is popular based on the analysis, determining the reason comprising, when the content identifies the search topic, providing at least some of the content as the reason that the search topic is popular;
• and
• presenting to a user the search topic that is popular and the determined reason that the search topic is popular;
• and
• summarizing content of more than one content feed when the content of more than one content feed relates to the same particular entity as the search topic.